AI Threat Alert

AI Security Threat Feed

Latest CVEs affecting AI/ML systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers. Vulnerabilities are tracked from NVD, GitHub Advisory, CISA KEV, MITRE ATLAS, and enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings to ISO 42001, EU AI Act, NIST AI RMF, and OWASP LLM Top 10. Updated continuously as new CVEs are published.

Sources
Each CVE is enriched with
  • CVSS severity
  • EPSS exploit probability
  • Exploitation confidence
  • AI-component classification
  • Compliance mappings
4,307

AI/ML CVEs Tracked

533

Critical

95

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 1961 results — Active exploitation
HIGHEXPLOIT AVAIL

PraisonAI: RCE via broken AST sandbox in workflows

CVE-2026-61438
7.3
EPSS 0.3%
Code ExecutionSupply ChainAgentPlugin
PraisonAICWE-7814 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: missing webhook signature check spoofs agents

CVE-2026-61436
8.6
EPSS 0.4%
Auth BypassSocial EngineeringAgentAPI
PraisonAICWE-28714 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: Host header spoof bypasses agent auth

CVE-2026-61435
8.2
EPSS 0.5%
Auth BypassAgentAPI
PraisonAICWE-28713 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: code injection via unsafe config codegen

CVE-2026-61433
7.8
EPSS 0.2%
Code ExecutionFrameworkAgentAPI
PraisonAICWE-9413 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: DNS rebinding SSRF bypass in web_crawl

CVE-2026-61430
8.5
EPSS 0.3%
Auth BypassData LeakageAgentPlugin
PraisonAICWE-20013 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI: MCP server auth bypass by default

CVE-2026-61427
7.3
EPSS 0.4%
Auth BypassCode ExecutionAgentPlugin
PraisonAICWE-2013 ATLAS
MEDIUMEXPLOIT AVAIL

PraisonAI: approval caching flaw enables file write abuse

CVE-2026-60087
6.1
EPSS 0.3%
Auth BypassCode ExecutionAgent
PraisonAICWE-86313 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: CORS misconfig + CSRF enables admin RCE

CVE-2026-56400
8.3
EPSS 0.5%
Auth BypassCode ExecutionSocial EngineeringPluginFramework
open-webuiCWE-61324 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: OAuth avatar stored XSS risks account takeover

CVE-2026-56398
7.3
EPSS 0.6%
Auth BypassCode ExecutionData LeakageFrameworkAPI
open-webui23 ATLAS
MEDIUMEXPLOIT AVAIL

jadx-gui: HTML injection in APK Summary tab leaks IP

CVE-2026-42447
5.0
EPSS 0.2%
Data LeakagePrivacy ViolationFramework
CWE-791 ATLAS
HIGHEXPLOIT AVAIL

yutu: arbitrary file write via MCP caption-download tool

CVE-2026-50158
7.7
EPSS 0.2%
Code ExecutionDoSPrompt InjectionAgentPlugin
github.com/eat-pray-ai/yutuPatch: 0.10.9-dev1CWE-736424 ATLAS
LOWEXPLOIT AVAIL

Keras: symlink bypass enables tar path traversal

CVE-2026-12482
3.1
EPSS 0.3%
Supply ChainCode ExecutionFrameworkModel
kerasPatch: 3.12.3CWE-224.1K4 ATLAS
LOWEXPLOIT AVAIL

wandb: weak hash weakens artifact integrity check

CVE-2026-15605
3.1
EPSS 0.2%
Supply ChainModel PoisoningTraining DataModel
wandbCWE-3271.3K2 ATLAS
HIGHEXPLOIT AVAIL

CrewAI: SSRF filter bypass via DNS rebinding

CVE-2026-62240
7.4
EPSS 0.5%
Auth BypassData LeakageAgentFramework
crewaiCWE-9183713 ATLAS
HIGHEXPLOIT AVAIL

Decidim: JWT replay bypasses multi-tenant isolation

CVE-2026-45414
8.5
EPSS 0.5%
Auth BypassPrivacy ViolationData LeakageAPIFramework
decidimPatch: 0.31.5CWE-287514
MEDIUMEXPLOIT AVAIL

HashNeRF: torch.load deserialization allows local RCE

CVE-2026-15531
5.3
EPSS 0.3%
Code ExecutionSupply ChainModelFramework
CWE-203 ATLAS
MEDIUMEXPLOIT AVAIL

n8n-workflow-builder: path traversal via filePath arg

CVE-2026-15521
5.3
EPSS 0.2%
Data LeakageCode ExecutionAgentPlugin
CWE-222 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: RCE via unsandboxed LLM code execution

CVE-2026-61447
10.0
EPSS 15.2%
Prompt InjectionCode ExecutionAgent
praisonaiCWE-9415 ATLAS
CRITICALEXPLOIT AVAIL

PraisonAI: AICoder root RCE via unsanitized tool calls

CVE-2026-61445
9.9
EPSS 0.6%
Code ExecutionPrompt InjectionAgentPlugin
praisonaiPatch: 4.6.78CWE-2215 ATLAS
HIGHEXPLOIT AVAIL

PraisonAI Platform: workspace members bypass owner authz

CVE-2026-61442
7.1
EPSS 0.3%
Auth BypassAgentFramework
praisonai-platformPatch: 0.1.9CWE-86212 ATLAS

Frequently asked questions

What is an AI security threat feed?

An AI security threat feed is a continuously updated stream of vulnerabilities (CVEs) affecting AI and machine-learning systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — filtered out of the broader CVE firehose and enriched for relevance.

Which sources are the AI CVEs tracked from?

CVEs are tracked from NVD, GitHub Advisory, CISA KEV, and MITRE ATLAS, then enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings.

What AI systems do these vulnerabilities affect?

Coverage spans LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — the components most security teams now run in production.

How often is the AI threat feed updated?

The feed updates continuously as new CVEs are published and enriched, so the most recent AI/ML vulnerabilities appear at the top.

Is the AI security feed free?

Yes — the public feed is free to browse. A Pro subscription adds breaking alerts, MITRE ATLAS mappings, compliance reports (ISO 42001, EU AI Act), and full CISO analysis.

Need deeper analysis?

Get ATLAS technique mappings, compliance reports (ISO 42001, EU AI Act), breaking alerts, and full CISO analysis with a Pro subscription.

Start 14-Day Free Trial